AI Seminar

Low-Rank Spectral Learning for Predictive State Representations

Alex Kulesza

University of Michigan
Tuesday, February 17, 2015
4:00pm - 5:30pm
3725 BBB

Add to Google Calendar

About the Event

In many settings we experience the world as a sequence of observations. For instance, we might observe the daily weather, read the words in a document, or receive a series of frames from a security camera. We would like to extract from these data a model of the world that allows us to make predictions: the probability of rain on Friday, the next word likely to be typed by a smartphone user, or whether to call the police.

Predictive state representations (PSRs), which generalize HMMs and POMDPs, model these kinds of problems by using predictions about future events as a representation of the current state. PSRs are appealing in part because they arise naturally from a spectral learning algorithm that computes PSR parameters in closed form using data statistics, thus avoiding traditional optimization procedures that are often slow and inexact. In theory, the spectral learning algorithm is not only fast but also statistically consistent; however, as I discussed at the AI seminar last year, the assumptions needed for consistency are rarely if ever met in practice. Morever, when those assumptions are even slightly violated, the learned parameters can be arbitrarily bad.

In this talk I will describe our recent work addressing the use of spectral learning for PSRs under more realistic assumptions. Our work is based on a theoretical analysis of a particular limiting case for spectral learning, which we show has some interesting and appealing properties. This analysis motivates several practical techniques, which we show lead to significantly better results on synthetic and real-world data.


Alex Kulesza is a postdoc in CSE.

Additional Information

Sponsor(s): Toyota

Open to: Public